GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
OnAnOrange
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OnAnOrange
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
cua-lite/Lite.OSWorld-v1 at revision
0c5d2495f35a27eae7baf8aa50b2e677b209de39: 1,937 examplescua-lite/Lite.CUAGym-v1 at revision
92fff449649d210bdfca09b71d4094900f8d5147: 1,788 examplesThe data was exported from
examples/lite/v1/configs/qwen3_5/reasoning/lite.osworld.yaml, changing only
agent_kwargs.resolution from [1024, 768] to [1920, 1080]. Qwen3.5's
32-pixel vision-grid alignment produces processed images of 1920x1088.
5e-61e-60.219431Only the final checkpoint was retained. The weights in this repository are the
final Hugging Face export from Slurm job 1879517 (eval-bbq-2).